A Generalized Unbiased Risk Estimator for Learning with Augmented Classes

In contrast to the standard learning paradigm where all classes can be observed in training data, with augmented (LAC) tackles problem unobserved data may emerge test phase. Previous research showed that given unlabeled an unbiased risk estimator (URE) derived, which minimized for LAC theoretical guarantees. However, this URE is only restricted specific type of one-versus-rest loss functions multi-class classification, making it not flexible enough when needs changed dataset practice. paper, we propose a generalized equipped arbitrary while maintaining guarantees, LAC. To alleviate issue negative empirical commonly encountered by previous studies, further novel risk-penalty regularization term. Experiments demonstrate effectiveness our proposed method.